Related papers: Table Pre-training: A Survey on Model Architecture…

User modeling is critical for many personalized web services. Many existing methods model users based on their behaviors and the labeled data of target tasks. However, these methods cannot exploit useful information in unlabeled user…

We present a neural semi-supervised learning model termed Self-Pretraining. Our model is inspired by the classic self-training algorithm. However, as opposed to self-training, Self-Pretraining is threshold-free, it can potentially update…

Understanding the connections between unstructured text and semi-structured table is an important yet neglected problem in natural language processing. In this work, we focus on content-based table retrieval. Given a query, the task is to…

Relational databases underpin critical infrastructure across a wide range of domains, yet the design of generalizable pre-training strategies for learning from relational databases remains an open challenge due to task heterogeneity.…

Data preparation is a critical step in enhancing the usability of tabular data and thus boosts downstream data-driven tasks. Traditional methods often face challenges in capturing the intricate relationships within tables and adapting to…

Tables are everywhere, from scientific journals, papers, websites, and newspapers all the way to items we buy at the supermarket. Detecting them is thus of utmost importance to automatically understanding the content of a document. The…

Table understanding is key to addressing challenging downstream tasks such as table-based question answering and fact verification. Recent works have focused on leveraging Chain-of-Thought and question decomposition to solve complex…

Recent methods based on pre-trained language models have exhibited superior performance over tabular tasks (e.g., tabular NLI), despite showing inherent problems such as not using the right evidence and inconsistent predictions across…

Tables on the Web contain a vast amount of knowledge in a structured form. To tap into this valuable resource, we address the problem of table retrieval: answering an information need with a ranked list of tables. We investigate this…

Reasoning over tabular data requires both table structure understanding and a broad set of table reasoning skills. Current models with table-specific architectures and pre-training methods perform well on understanding table structures, but…

Although great progress has been made by previous table understanding methods including recent approaches based on large language models (LLMs), they rely heavily on the premise that given tables must be converted into a certain text…

The recent rapid progress in pre-training Large Language Models has relied on using self-supervised language modeling objectives like next token prediction or span corruption. On the other hand, Machine Translation Systems are mostly…

Table reasoning, which aims to generate the corresponding answer to the question following the user requirement according to the provided table, and optionally a text description of the table, effectively improving the efficiency of…

Tabular data remains one of the most prevalent data types across a wide range of real-world applications, yet effective representation learning for this domain poses unique challenges due to its irregular patterns, heterogeneous feature…

Table entailment, the binary classification task of finding if a sentence is supported or refuted by the content of a table, requires parsing language and table structure as well as numerical and discrete reasoning. While there is extensive…

The first phase of table recognition is to detect the tabular area in a document. Subsequently, the tabular structures are recognized in the second phase in order to extract information from the respective cells. Table detection and…

In long document controllable summarization, where labeled data is scarce, pretrained models struggle to adapt to the task and effectively respond to user queries. In this paper, we introduce Socratic pretraining, a question-driven,…

Deep tabular modelling increasingly relies on in-context learning where, during inference, a model receives a set of $(x,y)$ pairs as context and predicts labels for new inputs without weight updates. We challenge the prevailing view that…

Deep neural networks are typically trained under a supervised learning framework where a model learns a single task using labeled data. Instead of relying solely on labeled data, practitioners can harness unlabeled or related data to…

Semi-structured tables are ubiquitous. There has been a variety of tasks that aim to automatically interpret, augment, and query tables. Current methods often require pretraining on tables or special model architecture design, are…